Character Analysis using Matra Segmentation Algorithms for Distorted Tamil Characters

Vol.4 No.2

Year: 2009

Issue: October - December

Title: Character Analysis using Matra Segmentation Algorithms for Distorted Tamil Characters   

Author Name: R. Indra Gandhi, K. Iyakutti   

Synopsis:   

Segmentation is an important phase towards designing an optical character recognition system. Most of the segmentation algorithms primarily aim at segmenting text, graphics, page, line and word. It is a critical step as most recognition errors occur due to incorrect segmentation of characters. Character segmentation is the fundamental process in character recognition approaches, which rely on isolated characters. The accuracy of the text recognition system heavily depends on character segmentation.  All the techniques that already exist do not work well when the document contains distorted characters. Special care on “Matra” is needed to segment distorted characters. In this paper, we have empirically implemented algorithms for solving the key problems of distorted characters segmentation. Experimental results show that the proposed technique is accurate, easy for extension, and may be very effective for non-headline based complex Indic scripts.